REGRESSION ANALYSIS

Regression analysis



Regression analysis

As organizations are routinely bombarded with a plethora of constantly changing and complex quantitative information, analytical procedures are being utilized to absorb and make use of this information in a sophisticated fashion. Just in the past decade, millions of business people have discovered that one of the most effective ways to analyze and evaluate decision alternatives involves using electronic spreadsheets to analytically model the decisions they face. Using spreadsheet models, a business person can effectively analyze decision alternatives before choosing a specific plan for implementation.

Spreadsheet modeling can primarily assist audit departments by enhancing their productivity through improved audit focus. Using a structured modeling approach to decision making will produce, on average, good outcomes more frequently than making decisions in a haphazard manner. Questions such as, “Do I need to perform more a detailed review for duplicate payments this month or is the risk of loss at an acceptable level?” can be easily answered using this approach. In essence, one of the main objectives of modeling, as it relates to auditing, is to match the limited resources of the department to the business risks associated with not meeting business objectives. The response variable may be non-continuous ("limited" to lie on some subset of the real line). For binary (zero or one) variables, if analysis proceeds with least-squares linear regression, the model is called the linear probability model. Nonlinear models for binary dependent variables include the probit and logit model. The multivariate probit model is a standard method of estimating a joint relationship between several binary dependent variables and some independent variables. For categorical variables with more than two values there is the multinomial logit. For ordinal variables with more than two values, there are the ordered logit and ordered probit models. Censored regression models may be used when the dependent variable is only sometimes observed, and Heckman correction type models may be used when the sample is not randomly selected from the population of interest. An alternative to such procedures is linear regression based on polychoric correlation (or polyserial correlations) between the categorical variables. Such procedures differ in the assumptions made about the distribution of the variables in the population. If the variable is positive with low values and represents the repetition of the occurrence of an event, then count models like the Poisson regression or the negative binomial model may be used.

Analytical Procedures - A Primer

“Analytical auditing procedures are performed by studying and comparing relationships among both financial and nonfinancial information” (Internal Auditors Statement on Internal Auditing Standards No. 8). The range of analyitcal procedures include:

comparisons - e.g., between the current and prior year account balances

ratio analysis - e.g., calculations of inventory turnover or times interest earned ratios.

reasonableness tests - e.g., estimating a given balance and comparing this estimate to the actual balance.

regression analysis - e.g., statistically estimating the payroll expense based on the number of employees, average rate of pay, and the number of hours worked.

Analytical procedures should be used in audit planning to assist ...